databricks-openai
Support for Databricks AI support with OpenAI
Decision gist · record as of 2026-08-14
Yes, if you are building OpenAI applications that need to retrieve context from Databricks vector indexes. The low install friction, active maintenance, permissive license, and no known vulnerabilities make it a safe choice. The package is narrowly scoped to a specific integration pattern, so install only if you have both Databricks infrastructure and OpenAI API access.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; Databricks workspace with a configured vector search index; OpenAI API key.
- Low friction install with a pure-Python wheel.
- Active maintenance status and recent releases.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions.
last release 2026-06-25 (50 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,448,755 downloads/mo, #3,886 on PyPI
Alternatives
Verify before relying
pip install databricks-openai
from databricks_openai import VectorSearchRetrieverTool
import json
from openai import OpenAI
client = OpenAI()
dbvs_tool = VectorSearchRetrieverTool(index_name="catalog.schema.my_index")
messages = [{"role": "user", "content": "Answer based on Databricks docs"}]
response = client.chat.completions.create(
model="gpt-4o",
messages=messages,
tools=[dbvs_tool.tool]
)- Whether VectorSearchRetrieverTool requires pre-existing Databricks vector indexes or can create them
- Support for embedding models other than OpenAI's default
- Performance characteristics with large vector indexes or high query volume
What it is and what it does
databricks-openai bridges Databricks AI capabilities into OpenAI-based applications by providing tool definitions that work with OpenAI's function-calling API. The primary use case is retrieval-augmented generation (RAG): it wraps Databricks vector search indexes as callable tools that OpenAI models can invoke during chat completions to fetch relevant context before generating responses.
The package depends on eight runtime libraries including databricks-ai-bridge, mlflow, openai, pydantic, and several Databricks-specific modules. It requires Python 3.10 or later and installs as a pure-Python wheel with low friction. The integration follows OpenAI's standard tool-use pattern: define a VectorSearchRetrieverTool pointing to a Databricks index, pass it to the chat completions API, parse the model's tool calls, execute the retrieval, and feed results back to the model.
Use it for
- Build RAG systems where OpenAI models query Databricks vector indexes to ground responses in proprietary data
- Create chatbots that retrieve context from Databricks documentation or knowledge bases before answering user questions
- Integrate Databricks AI Search with OpenAI agents for multi-step reasoning over indexed data
- Combine MLflow model tracking with OpenAI function calling for reproducible, retrieval-augmented workflows
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building OpenAI applications that need to retrieve context from Databricks vector indexes.
The low install friction, active maintenance, permissive license, and no known vulnerabilities make it a safe choice. The package is narrowly scoped to a specific integration pattern, so install only if you have both Databricks infrastructure and OpenAI API access.
Install
databricks-openai on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance status and recent releases. Requires Python 3.10 or later.
Requires Python 3.10 or later; Databricks workspace with a configured vector search index; OpenAI API key.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions.
Quickstart
pip install databricks-openai
from databricks_openai import VectorSearchRetrieverTool
import json
from openai import OpenAI
client = OpenAI()
dbvs_tool = VectorSearchRetrieverTool(index_name="catalog.schema.my_index")
messages = [{"role": "user", "content": "Answer based on Databricks docs"}]
response = client.chat.completions.create(
model="gpt-4o",
messages=messages,
tools=[dbvs_tool.tool]
)Verify before relying
- Whether VectorSearchRetrieverTool requires pre-existing Databricks vector indexes or can create them
- Support for embedding models other than OpenAI's default
- Performance characteristics with large vector indexes or high query volume
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagesdatabricks-ai-bridgedatabricks-ai-searchdatabricks-mcpmlflowopenai-agentsopenaipydanticunitycatalog-openai |
| Maintenance | Actively maintained 50 days since the last release |
| First released | |
| Downloads | 1,448,755 / month, #3,886 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: databricks_openai-0.17.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “databricks vector search openai”
- databricks-openaiIntegrates Databricks AI features, particularly vector search, into…
- databricks-ai-bridgeProvides a shared Python API layer for building agents and…
- databricks-ai-searchPython client for Databricks AI Search, a managed vector and keyword…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also databricks-ai-bridge · unitycatalog-openai · langchain-databricks · databricks-langchain · databricks-ai-search · llama-index-embeddings-azure-openai · databricks-mcp · databricks-vectorsearch · llama-index-embeddings-openai · unitycatalog-ai